A Hybrid CNN-LSTM Model for Forecasting Particulate Matter (PM2.5)

PM2.5 is one of the most important pollutants related to air quality, and the increase of its concentration will aggravate the threat to people’s health. Therefore, the prediction of surface PM2.5 concentration is of great significance to human health protection. In this study, A hybrid CNN-LSTM model is developed by combining the convolutional neural network (CNN) with the long short-term memory (LSTM) neural network for forecasting the next 24h PM2.5 concentration in Beijing, which makes full use of their advantages that CNN can effectively extract the features related to air quality and the LSTM can reflect the long term historical process of input time series data. The air quality data of the last 7days and the PM2.5 concentration of the next day are first set as the input and output of the model due to the periodicity, respectively. Subsequently four models namely univariate LSTM model, multivariate LSTM model, univariate CNN-LSTM model and multivariate CNN-LSTM model, are established for PM2.5 concentration prediction. Finally, mean absolute error (MAE) and root mean square error (RMSE) are employed to evaluate the performance of these models and results show that the proposed multivariate CNN-LSTM model performs the best results due to low error and short training time.

[1]  James L. McClelland,et al.  Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

[2]  Garima,et al.  Review on time series databases and recent research trends in Time Series Mining , 2014, 2014 5th International Conference - Confluence The Next Generation Information Technology Summit (Confluence).

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[5]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[6]  Jianfeng Zhao,et al.  Speech emotion recognition using deep 1D & 2D CNN LSTM networks , 2019, Biomed. Signal Process. Control..

[7]  Peter E.D. Love,et al.  A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory , 2018 .

[8]  C. Chan,et al.  Air pollution in mega cities in China , 2008 .

[9]  Ping-Huan Kuo,et al.  A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities , 2018, Sensors.

[10]  A. Piazzalunga,et al.  High secondary aerosol contribution to particulate pollution during haze events in China , 2014, Nature.

[11]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[12]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[13]  Billy M. Williams,et al.  Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models , 1998 .

[14]  A. Peters,et al.  Particulate Matter Air Pollution and Cardiovascular Disease: An Update to the Scientific Statement From the American Heart Association , 2010, Circulation.

[15]  Yun Yang,et al.  Improved Deep Hybrid Networks for Urban Traffic Flow Prediction Using Trajectory Data , 2018, IEEE Access.

[16]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[17]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[18]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[19]  Min Shao,et al.  Chemical composition and quantitative relationship between meteorological condition and fine particles in Beijing. , 2004, Journal of environmental sciences.

[20]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[21]  U. Rajendra Acharya,et al.  Arrhythmia detection using deep convolutional neural network with long duration ECG signals , 2018, Comput. Biol. Medicine.

[22]  Kyongjin Sok,et al.  A hybrid model based on convolutional neural networks and long short-term memory for ozone concentration prediction , 2018, Air Quality, Atmosphere & Health.

[23]  Shiliang Sun,et al.  A bayesian network approach to traffic flow forecasting , 2006, IEEE Transactions on Intelligent Transportation Systems.

[24]  J. Seinfeld.  Air pollution: A half century of progress , 2004 .

[25]  Jiachen Zhao,et al.  Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. , 2019, Chemosphere.

[26]  J. Schwartz,et al.  Is Daily Mortality Associated Specifically with Fine Particles? , 1996, Journal of the Air & Waste Management Association.

[27]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[28]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[30]  Liang Zhao,et al.  Time series trend detection and forecasting using complex network topology analysis , 2019, Neural Networks.

[31]  J. Lelieveld,et al.  The contribution of outdoor air pollution sources to premature mortality on a global scale , 2015, Nature.

[32]  Onur Avci,et al.  Wireless and real-time structural damage detection: A novel decentralized method for wireless sensor networks , 2018, Journal of Sound and Vibration.

[33]  Eman M. G. Younis,et al.  Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection , 2019, Inf. Fusion.